GRIAL resources
Permanent URI for this communityhttps://repositorio.grial.eu/handle/123456789/1
Browse
4 results
Search Results
Item Are Textual Recommendations Enough? Guiding Physicians Toward the Design of Machine Learning Pipelines Through a Visual Platform(Springer, 2023-09-05) Vázquez-Ingelmo, A.; García-Holgado, A.; García-Peñalvo, F. J.; Pérez-Sánchez, P.; Antúnez-Muiños, P.; Sánchez-Puente, A.; Vicente-Palacios, V.; Dorado-Díaz, P. I.; Sánchez, P. L.The prevalence of artificial intelligence (AI) in our daily lives is often exaggerated by the media, leading to a positive public perception while overlook-ing potential problems. In the field of medicine, it is crucial to educate future health-care professionals on the advantages and disadvantages of AI and to emphasize the importance of creating fair, ethical, and reproducible models. The KoopaML platform was developed to provide an educational and user-friendly interface for inexperienced users to create AI pipelines. This study analyzes the quantitative and interaction data gathered from a usability test involving physicians from the University Hospital of Salamanca, with the aim of identifying new interaction paradigms to improve the platform’s usability. The results shown that the plat-form is difficult to learn for inexperienced users due to its contents related to AI. Following these results, a set of improvements are proposed for the next version of KoopaML, focusing on reducing the interactions needed to create the pipelines.Item Flexible Heuristics for Supporting RecommendationsWithin an AI Platform Aimed at Non-expert Users(Springer, 2023-05-01) Vázquez-Ingelmo, A.; García-Holgado, A.; García-Peñalvo, F. J.; Andrés-Fraile, E.; Pérez-Sánchez, P.; Antúnez-Muiños, P.; Sánchez-Puente, A.; Vicente-Palacios, V.; Dorado-Díaz, P. I.; Cruz-González, I.; Sánchez, P. L.The use of Machine Learning (ML) to resolve complex tasks has become popular in several contexts. While these approaches are very effective and have many related benefits, they are still very tricky for the general audi-ence. In this sense, expert knowledge is crucial to apply ML algorithms properly and to avoid potential issues. However, in some situations, it is not possible to rely on experts to guide the development of ML pipelines. To tackle this issue, we present an approach to provide customized heuristics and recommendations through a graphical platform to build ML pipelines, namely KoopaML, focused on the medical domain. With this approach, we aim not only at providing an easy way to apply ML for non-expert users, but also at providing a learning experience for them to understand how these methods work.Item Psychiatric patients tracking through a private social network for relatives: development and pilot study(Springer, 2016-07) García-Peñalvo, F. J.; Franco Martín, M.; García-Holgado, A.; Toribio Guzmán, J. M.; Largo Antón, J.; Sánchez-Gómez, M. C.The treatment of psychiatric patients requires different health care from that of patients from other medical specialties. In particular, in the case of Department of Psychiatry from the Zamora Hospital (Spain), the period of time which patients require institutionalized care is a tiny part of their treatment. A large part of health care provided to the patient is aimed at his/her rehabilitation and social integration through day-care centres, supervised flats or activities. Conversely, several reports reveal that approximately 50% of Internet users use the network as a source of health information, which has led to the emergence of virtual communities where patients, relatives or health professionals share their knowledge concerning an illness, health problem or specific health condition. In this context, we have identified that the relatives have a lack of information regarding the daily activities of patients under psychiatric treatment. The social networks or the virtual communities regarding health problems do not provide a private space where relatives can follow the patient's progress, despite being in different places. The goal of the study was to use technologies to develop a private social network for being used by severe mental patients (mainly schizophrenic patients). SocialNet is a pioneer social network in the health sector because it provides a social interaction context restricted to persons authorized by the patient or his/her legal guardian in such a way that they can track his/her daily activity. Each patient has a private area only accessible to authorized persons and their caregivers, where they can share pictures, videos or texts regarding his/her progress. A preliminary study of usability of the system has been made for increasing the usefulness and usability of SocialNet. SocialNet is the first system for promoting personal interactions among formal caregivers, family, close friends and patient, promoting the recovery of schizophrenic patients. Future studies should study the network’s potential usefulness for improving the prognosis and recovery of schizophrenia.Item Usability Evaluation of a Private Social Network on Mental Health for Relatives(Springer, 2017-10-31) Toribio-Guzmán, J. M.; García-Holgado, A.; Soto Pérez, F.; García-Peñalvo, F. J.; Franco Martín, M.Usability is one of the most prominent criteria that must be fulfilled by a software product. This study aims to evaluate the usability of SocialNet, a private social network for monitoring the daily progress of patients by their relatives, using a mixed usability approach: heuristic evaluation con-ducted by experts and user testing. A double heuristic evalu-ation with one expert evaluator identified the issues related to consistency, design, and privacy. User testing was conducted on 20 users and one evaluator using observation techniques and questionnaires. The main usability problems were found to be related to the structure of SocialNet, and the users pre-sented some difficulties in locating the buttons or links. The results show a high level of usability and satisfaction with the product. This evaluation provides data on the usability of SocialNet based on the difficulties experienced by the users and the expert. The results help in redesigning the tool to resolve the identified problems as part of an iterative process.